CN110388773A - Fault detection method, system and the water cooler of water cooler - Google Patents
Fault detection method, system and the water cooler of water cooler Download PDFInfo
- Publication number
- CN110388773A CN110388773A CN201910637549.4A CN201910637549A CN110388773A CN 110388773 A CN110388773 A CN 110388773A CN 201910637549 A CN201910637549 A CN 201910637549A CN 110388773 A CN110388773 A CN 110388773A
- Authority
- CN
- China
- Prior art keywords
- water cooler
- failure
- operation data
- data
- fault detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25B—REFRIGERATION MACHINES, PLANTS OR SYSTEMS; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS
- F25B49/00—Arrangement or mounting of control or safety devices
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25B—REFRIGERATION MACHINES, PLANTS OR SYSTEMS; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS
- F25B2500/00—Problems to be solved
- F25B2500/06—Damage
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Thermal Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Air Conditioning Control Device (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application proposes fault detection method, system and the water cooler of a kind of water cooler.Wherein, the fault detection method of water cooler, comprising: obtain the failure operation data of water cooler;Over-sampling is carried out to the failure operation data, to obtain failure missing data;Fault characteristic parametric prediction model is established according to the failure operation data and failure missing data;Judge whether the operation data of the water cooler is abnormal according to the fault characteristic parametric prediction model.The fault detection method of the water cooler of the application has the advantages that detection is accurate, reliable, furthermore it is possible to detection is effectively reduced for the occupancy of resource, thus, be conducive to implement in water cooler, promote the reliability of water cooler.
Description
Technical field
This application involves technical field of refrigeration equipment, in particular to a kind of fault detection method of water cooler, system and
Water cooler.
Background technique
In the related technology, the fault detection means of water cooler include carrying out fault verification based on expertise setting rule
Method, based on supervised study classification method and based on operate normally data establish model, to real-time running data carry out
The method of residual analysis.
Wherein, fault verification is carried out based on expertise setting rule, such as is generated according to ermal physics knowledge analysis failure
When the parameters such as heat transfer temperature difference, pressure, temperature, electric current variation tendency, and respective threshold is set, so as to according to variation tendency
Determine failure.Based on the classification method of supervised study, different faults under various working conditions are obtained by fault simulating test
Operation data when generation, and normal data composition data library to data classification and label respectively, then utilize neural network
Or support vector machines scheduling algorithm establishes black-box model, so that model is correctly classified operation data by training, to realize
The purpose of fault detection and diagnosis.Model is established based on data are operated normally, the side of residual analysis is carried out to real-time running data
Method, this method to operate normally data carry out characterisitic parameter recurrence, establish characterisitic parameter prediction model, to real-time running data with
Predicted value compares, and the operation data to residual error beyond threshold value is as troubleshooting.
Have the disadvantage in that setting regular failure judgment method based on expertise identifies that apparent failure is more effective,
But since the variation of parameter is usually influenced by Multiple factors, Yi Zao undesirable for the detection effect at fault progression initial stage
At leak detection or error detection;Classification method based on supervised study is preferable for the detection and diagnosis effect of failure, but needs
It is realized based on a large amount of fault test data, investment resource is excessively high, and model generalization is indifferent, and unstable state data are identified
It is difficult;Model is established based on data are operated normally, the method for carrying out residual analysis to real-time running data does not have failure modes
Effect, it is limited after all additionally, due to the normal operation data for establishing initial model, therefore, encountering outside modeling floor data just
Error detection will likely occur in normal operation data.
Summary of the invention
The application aims to solve at least one of above-mentioned technical problem.
For this purpose, the purpose of the application is to propose a kind of fault detection method of water cooler.This method has inspection
Accurate, reliable advantage is surveyed, furthermore it is possible to detection is effectively reduced for the occupancy of resource, thus, be conducive in water cooler
Implement, promotes the reliability of water cooler.
Second purpose of the application is to propose a kind of fault detection system of water cooler.
The third purpose of the application is to propose a kind of computer readable storage medium.
The 4th purpose of the application is to propose a kind of water cooler.
To achieve the goals above, the first aspect of the application discloses a kind of fault detection method of water cooler, packet
It includes: obtaining the failure operation data of water cooler;Over-sampling is carried out to the failure operation data, to obtain failure missing number
According to;Fault characteristic parametric prediction model is established according to the failure operation data and failure missing data;It is special according to the failure
Property parametric prediction model judge whether the operation data of the water cooler abnormal.
The fault detection method of the water cooler of the application has the advantages that detection is accurate, reliable, furthermore it is possible to effectively
Detection is reduced for the occupancy of resource, thus, be conducive to implement in water cooler, promote the reliability of water cooler.
In some instances, described that over-sampling is carried out to the failure operation data, to obtain failure missing data, packet
It includes: classifying to the failure operation data, to establish multiple Mishap Databases, wherein each Mishap Database storage one
Class failure operation data;According to the new data of the adjacent failure operation data creation in each Mishap Database, and will be described new
Data as the failure missing data.
In some instances, before carrying out over-sampling to the failure operation data, further includes: to the failure operation
Data are removed dryness.
It is in some instances, described that according to the failure operation data and failure missing data to establish fault characteristic parameter pre-
Survey model, comprising: characterisitic parameter recurrence is carried out according to the failure operation data in multiple Mishap Databases respectively, to establish difference
Multiple fault characteristic parametric prediction models corresponding to multiple Mishap Databases.
In some instances, the operation number that the water cooler is judged according to the fault characteristic parametric prediction model
According to whether abnormal, comprising: determine the operation data predicted value of water cooler according to the fault characteristic parametric prediction model;It obtains
Residual error between the operation data of the water cooler and the operation data predicted value of the water cooler;Sentenced according to the residual error
The water cooler of breaking whether there is failure.
In some instances, the failure operation data for obtaining water cooler, comprising: transported according to the failure of water cooler
Row experiment, obtains the failure operation data of the water cooler;And/or history run number when water cooler breaks down
According to the failure operation data as the water cooler.
The second aspect of the application discloses a kind of fault detection system of water cooler, comprising: module is obtained, for obtaining
Take the failure operation data of water cooler;Over-sampling module, for carrying out over-sampling to the failure operation data, to obtain event
Hinder missing data;Model creation module, for establishing fault characteristic ginseng according to the failure operation data and failure missing data
Number prediction model;Fault diagnosis module, for judging the fortune of the water cooler according to the fault characteristic parametric prediction model
Whether row data are abnormal.
The fault detection system of the water cooler of the application has the advantages that detection is accurate, reliable, furthermore it is possible to effectively
Detection is reduced for the occupancy of resource, thus, be conducive to implement in water cooler, promote the reliability of water cooler.
In some instances, the over-sampling module is multiple to establish for classifying to the failure operation data
Mishap Database, and the data new according to the adjacent failure operation data creation in each Mishap Database, and will be described new
Data are as the failure missing data, wherein each Mishap Database stores a kind of failure operation data;
In some instances, further includes: remove dryness module, for the over-sampling module to the failure operation data into
Before row over-sampling, the failure operation data are removed dryness.
In some instances, the model creation module is used for respectively according to the failure operation number in multiple Mishap Databases
According to characterisitic parameter recurrence is carried out, to establish the multiple fault characteristic parametric prediction models for corresponding respectively to multiple Mishap Databases.
In some instances, the fault diagnosis module is used to determine cold water according to the fault characteristic parametric prediction model
The operation data predicted value of unit, and the operation data for the operation data and the water cooler for obtaining the water cooler is predicted
Residual error between value, and judge the water cooler with the presence or absence of failure according to the residual error.
In some instances, the acquisition module is used to be tested according to the failure operation of water cooler, obtains the cold water
The failure operation data of unit, and/or, history data when water cooler is broken down is as the water cooler
Failure operation data.
The third aspect of the application discloses a kind of computer readable storage medium, is stored thereon with the failure of water cooler
Program is detected, water cooler described in above-mentioned first aspect is realized when the fault detection program of the water cooler is executed by processor
Fault detection method.
The fourth aspect of the application discloses a kind of water cooler, including memory, processor and storage are on a memory
And the fault detection program for the water cooler that can be run on a processor, the processor execute the failure inspection of the water cooler
The fault detection method of water cooler described in above-mentioned first aspect is realized when ranging sequence.The water cooler of the application has failure
Accurate, reliable advantage is detected, furthermore it is possible to detection is effectively reduced for the occupancy of resource, thus, promote water cooler can
By property.
The additional aspect and advantage of the application will be set forth in part in the description, and will partially become from the following description
It obtains obviously, or recognized by the practice of the application.
Detailed description of the invention
The above-mentioned and/or additional aspect and advantage combination following accompanying drawings of the application in the description of embodiment to will become
Obviously and it is readily appreciated that, in which:
Fig. 1 is the flow chart according to the fault detection method of the water cooler of the application one embodiment;
Fig. 2 is to be located at showing of showing in coordinate system according to the failure operation data of the water cooler of the application one embodiment
It is intended to;
Fig. 3 is to be located to sit according to the failure operation data and failure missing data of the water cooler of the application one embodiment
The schematic diagram shown in mark system;
Fig. 4 is illustrated according to the failure detection result of the fault detection method of the water cooler of the application one embodiment
Figure;
Fig. 5 is the implementation steps schematic diagram according to the fault detection method of the water cooler of the application one embodiment;
Fig. 6 is the structural block diagram according to the fault detection system of the water cooler of the application one embodiment.
Description of symbols:
The fault detection system 600 of water cooler, obtain module 610, over-sampling module 620, model creation module 630,
Fault diagnosis module 640.
Specific embodiment
Embodiments herein is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, and is only used for explaining the application, and should not be understood as the limitation to the application.
In the description of the present application, it is to be understood that term " center ", " longitudinal direction ", " transverse direction ", "upper", "lower",
The orientation or positional relationship of the instructions such as "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside" is
It is based on the orientation or positional relationship shown in the drawings, is merely for convenience of description the application and simplifies description, rather than instruction or dark
Show that signified device or element must have a particular orientation, be constructed and operated in a specific orientation, therefore should not be understood as pair
The limitation of the application.In addition, term " first ", " second " are used for description purposes only, it is not understood to indicate or imply opposite
Importance.
Below in conjunction with attached drawing description according to fault detection method, system and the cooling-water machine of the water cooler of the embodiment of the present application
Group.
Fig. 1 is the flow chart according to the control method of the water cooler of the embodiment of the present application.As shown in Figure 1, according to this Shen
Please one embodiment water cooler fault detection method, include the following steps:
S101: the failure operation data of water cooler are obtained.
Such as: it can be tested according to the failure operation of water cooler, obtain the failure operation data of water cooler;And/or
History data when water cooler is broken down is as the failure operation data of water cooler.
That is: the failure operation under different load, different temperatures (such as cooling water temperature) combination is carried out to water cooler to test,
To obtain the failure operation data under different load, different temperatures combination.Certainly, if there is fixed failure operation number
According to, it may be assumed that history data when water cooler breaks down then can be read directly.
S102: over-sampling is carried out to failure operation data, to obtain failure missing data.
In specific example, it can classify first to failure operation data, to establish multiple Mishap Databases, so
Afterwards, the data new according to the adjacent failure operation data creation in each Mishap Database, and using the new data as institute
State failure missing data.
Specifically, over-sampling is carried out to the failure operation data in Mishap Database using data oversampling technology, from
And the failure missing data such as operating condition interval can be made up.Over-sampling is that linearly connected, In are between failure operation data point
Wherein create new data.Such as: it include 20 data in failure operation data, by this 20 data as in coordinate system, this
Sample, available multiple new data on the linearly connected between 20 coordinate points.
As shown in Fig. 2, being the failure operation data presented in coordinate system, wherein a kind of point of shape represents a kind of data.
The failure missing data completed is created, as shown in figure 3, failure operation data and failure missing data to be presented in coordinate system,
Wherein, as shown failure operation data and failure missing data in Fig. 3 in dotted line frame.Wherein, failure operation data and failure
Missing data can become over-sampling data.
In the above description, each Mishap Database stores a kind of failure operation data.Such as: failure operation data are divided
For 10 classes, then it can establish 10 Mishap Databases, each Mishap Database stores a kind of failure operation data.
It should be noted that the standard classified to failure operation data can be true according to the actual demand of water cooler
It is fixed, such as: the corresponding failure operation data of each failure are directed to, same class is divided into.
It is, of course, also possible to classify according to other principles, also, the quantity classified can arbitrarily be increased and decreased.
S103: fault characteristic parametric prediction model is established according to failure operation data and failure missing data.
A fault characteristic parametric prediction model can be established for each Mishap Database.Specifically, basis respectively
Failure operation data in multiple Mishap Databases carry out characterisitic parameter recurrence, correspond respectively to multiple Mishap Databases to establish
Multiple fault characteristic parametric prediction models.
In specific example, fault characteristic parametric prediction model can be established by pca method.
S104: judge whether the operation data of water cooler is abnormal according to fault characteristic parametric prediction model.
In one embodiment of the application, the operation data of water cooler is judged according to fault characteristic parametric prediction model
It is whether abnormal, comprising: the operation data predicted value of water cooler is determined according to fault characteristic parametric prediction model;Obtain cooling-water machine
Residual error between the operation data of group and the operation data predicted value of water cooler;Judge that water cooler whether there is according to residual error
Failure.
That is, the prediction obtained by the real-time operation data of water cooler and by fault characteristic parametric prediction model
Value compares, and carries out residual analysis to real-time operation data, and the operation data to residual error lower than preset threshold is as abnormal
Data, in turn, determining water cooler, there are failures.Wherein, preset threshold can be by empirically determined.
As shown in Figure 4, wherein being located at dotted line data below indicates that residual error is lower than preset threshold, it may be assumed that failure operation number
According to expression water cooler breaks down.
According to the fault detection method of the water cooler of the embodiment of the present application, have the advantages that detection is accurate, reliable, separately
Outside, detection can be effectively reduced for the occupancy of resource, thus, be conducive to implement in water cooler, promote water cooler
Reliability.
The failure operation data of the fault detection method of the water cooler of the embodiment of the present application, water cooler can be with event
Hinder the continuous progress of detection and is continuously increased, in this way, fault characteristic parametric prediction model can be updated in real time, thus
The comprehensive and reliability for constantly promoting fault detection is effectively reduced leak detection, the probability that false retrieval is surveyed, is provided with for water cooler
Effect ensures.
In one embodiment of the application, before carrying out over-sampling to failure operation data, further includes: transported to failure
Row data are removed dryness.It is thus possible to further promote the accuracy and reliability of fault detection.
As shown in figure 5, the fault detection method of the water cooler of the embodiment of the present application is in specific implementation, comprising:
1, it inputs, it may be assumed that unit (water cooler) online monitoring data, it may be assumed that the monitoring real-time operation data of water cooler.
2, noise is removed, it may be assumed that remove dryness to the real-time operation data of water cooler.
3,1 model of failure, 2 model of failure to failure n model are established, wherein 1 model of failure, 2 model of failure to failure n
Model indicates the fault characteristic parametric prediction model established for the failure operation data in each Mishap Database.However, therefore
Hinder 1 model, 2 model of failure to failure n model can be run simultaneously, the real-time operation data of water cooler is analyzed, from
And determine water cooler with the presence or absence of failure.
The fault detection method of the water cooler of the embodiment of the present application returns the characteristic parameter of failure operation data
Return, in this way, the mode of artificial given threshold can be replaced to carry out fault detection, fault detection efficiency is improved, by using mistake
Sampling, makes up the vacancy of failure operation data, to significantly reduce the workload of test, has saved fault characteristic ginseng
The modeling cost of number prediction model, establishes fault characteristic parametric prediction model using failure operation data, avoids to unidentified
Operation data error detection, therefore, be not required to initially carry out the test of complete full working scope fault simulation obtain it is comprehensive therefore
Hinder operation data, fault characteristic parametric prediction model can be constantly improve in failure diagnostic process, it is thus possible to before reducing
Phase investment, in addition, by the fault characteristic parametric prediction model of multiclass failure can on-line checking simultaneously, not only may be implemented therefore
The classification of barrier can not also reduce the resource requirement of detection and diagnosis.
Fig. 6 is the structural block diagram according to the fault detection system of the water cooler of the application one embodiment.Such as Fig. 6 institute
Show, according to the fault detection system 600 of the water cooler of the application one embodiment, comprising: obtain module 610, over-sampling mould
Block 620, model creation module 630 and fault diagnosis module 640.
Wherein, the failure operation data that module 610 is used to obtain water cooler are obtained.Over-sampling module 620 is used for institute
It states failure operation data and carries out over-sampling, to obtain failure missing data.Model creation module 630 is used to be transported according to the failure
Row data and failure missing data establish fault characteristic parametric prediction model.Fault diagnosis module 640 is used for according to the failure
Characterisitic parameter prediction model judges whether the operation data of the water cooler is abnormal.
In one embodiment of the application, the over-sampling module 620 is for dividing the failure operation data
Class, to establish multiple Mishap Databases, and the data new according to the adjacent failure operation data creation in each Mishap Database,
And using the new data as the failure missing data, wherein each Mishap Database stores a kind of failure operation data;
In one embodiment of the application, further includes: module (being not shown in Fig. 6) is removed dryness, for adopting in the mistake
Before egf block carries out over-sampling to the failure operation data, the failure operation data are removed dryness.
In one embodiment of the application, the model creation module 630 is used for respectively according to multiple Mishap Databases
In failure operation data carry out characterisitic parameter recurrence, correspond respectively to multiple fault characteristics of multiple Mishap Databases to establish
Parametric prediction model.
In one embodiment of the application, the fault diagnosis module 640 is used for pre- according to the fault characteristic parameter
It surveys model and determines the operation data predicted value of water cooler, and obtain the operation data and the water cooler of the water cooler
Operation data predicted value between residual error, and judge the water cooler with the presence or absence of failure according to the residual error.
In one embodiment of the application, the acquisition module 610 is used to be tested according to the failure operation of water cooler,
The failure operation data of the water cooler are obtained, and/or, history data when water cooler is broken down is as institute
State the failure operation data of water cooler.
According to the fault detection system of the water cooler of the embodiment of the present application, have the advantages that detection is accurate, reliable, separately
Outside, detection can be effectively reduced for the occupancy of resource, thus, be conducive to implement in water cooler, promote water cooler
Reliability.
It should be noted that the specific implementation of the fault detection system of the water cooler of the embodiment of the present application and this Shen
Please embodiment water cooler fault detection method specific implementation it is similar, specifically refer to the description of method part,
In order to reduce redundancy, it is not repeated herein.
Further, embodiments herein discloses a kind of computer readable storage medium, is stored thereon with computer
Program is stored thereon with the fault detection program of water cooler, when the fault detection program of the water cooler is executed by processor
Realize the fault detection of above-mentioned water cooler.
Further, embodiments herein discloses a kind of water cooler, including memory, processor and is stored in
On reservoir and the fault detection program of water cooler that can run on a processor, the processor execute the water cooler
The fault detection method of above-mentioned water cooler is realized when fault detection program.The water cooler of the application has fault detection
Accurately, advantage reliably, furthermore it is possible to detection is effectively reduced for the occupancy of resource, thus, promote the reliable of water cooler
Property.
In addition, according to other compositions of the water cooler of the embodiment of the present application and effect for this field ordinary skill
All be for personnel it is known, in order to reduce redundancy, be not repeated herein.
Above-mentioned non-transitorycomputer readable storage medium can appointing using one or more computer-readable media
Meaning combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.Computer can
Reading storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device
Or device, or any above combination.The more specific example (non exhaustive list) of computer readable storage medium includes:
Electrical connection, portable computer diskette, hard disk, random access memory (RAM), read-only storage with one or more conducting wires
Device (Read Only Memory;Hereinafter referred to as: ROM), erasable programmable read only memory (Erasable
Programmable Read Only Memory;Hereinafter referred to as: EPROM) or flash memory, optical fiber, portable compact disc are read-only deposits
Reservoir (CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer
Readable storage medium storing program for executing can be any tangible medium for including or store program, which can be commanded execution system, device
Either device use or in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including --- but
It is not limited to --- electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be
Any computer-readable medium other than computer readable storage medium, which can send, propagate or
Transmission is for by the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In --- wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
Can with one or more programming languages or combinations thereof come write for execute the application operation computer
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
It further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.In
It is related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (Local
Area Network;Hereinafter referred to as: LAN) or wide area network (Wide Area Network;Hereinafter referred to as: WAN) it is connected to user
Computer, or, it may be connected to outer computer (such as being connected using ISP by internet).
While there has been shown and described that embodiments herein, it will be understood by those skilled in the art that: not
A variety of change, modification, replacement and modification can be carried out to these embodiments in the case where being detached from the principle and objective of the application, this
The range of application is by claim and its equivalent limits.
Claims (14)
1. a kind of fault detection method of water cooler characterized by comprising
Obtain the failure operation data of water cooler;
Over-sampling is carried out to the failure operation data, to obtain failure missing data;
Fault characteristic parametric prediction model is established according to the failure operation data and failure missing data;
Judge whether the operation data of the water cooler is abnormal according to the fault characteristic parametric prediction model.
2. the fault detection method of water cooler according to claim 1, which is characterized in that described to the failure operation
Data carry out over-sampling, to obtain failure missing data, comprising:
Classify to the failure operation data, to establish multiple Mishap Databases, wherein each Mishap Database storage one
Class failure operation data;
According to the new data of the adjacent failure operation data creation in each Mishap Database, and using the new data as institute
State failure missing data.
3. the fault detection method of water cooler according to claim 1 or 2, which is characterized in that transported to the failure
Row data carry out before over-sampling, further includes:
The failure operation data are removed dryness.
4. the fault detection method of water cooler according to claim 2, which is characterized in that described to be transported according to the failure
Row data and failure missing data establish fault characteristic parametric prediction model, comprising:
Characterisitic parameter recurrence is carried out according to the failure operation data in multiple Mishap Databases respectively, is corresponded respectively to foundation more
Multiple fault characteristic parametric prediction models of a Mishap Database.
5. the fault detection method of water cooler according to claim 2, which is characterized in that described special according to the failure
Property parametric prediction model judge whether the operation data of the water cooler abnormal, comprising:
The operation data predicted value of water cooler is determined according to the fault characteristic parametric prediction model;
Obtain the residual error between the operation data of the water cooler and the operation data predicted value of the water cooler;
Judge the water cooler with the presence or absence of failure according to the residual error.
6. the fault detection method of water cooler according to claim 1, which is characterized in that the acquisition water cooler
Failure operation data, comprising:
It is tested according to the failure operation of water cooler, obtains the failure operation data of the water cooler;And/or
History data when water cooler is broken down is as the failure operation data of the water cooler.
7. a kind of fault detection system of water cooler characterized by comprising
Module is obtained, for obtaining the failure operation data of water cooler;
Over-sampling module, for carrying out over-sampling to the failure operation data, to obtain failure missing data;
Model creation module, for establishing fault characteristic parameter prediction mould according to the failure operation data and failure missing data
Type;
Fault diagnosis module, for judging that the operation data of the water cooler is according to the fault characteristic parametric prediction model
No exception.
8. the fault detection system of water cooler according to claim 7, which is characterized in that the over-sampling module is used for
Classify to the failure operation data, to establish multiple Mishap Databases, and according to adjacent in each Mishap Database
The new data of failure operation data creation, and using the new data as the failure missing data, wherein each number of faults
A kind of failure operation data are stored according to library;
9. the fault detection system of water cooler according to claim 7 or 8, which is characterized in that further include:
Module is removed dryness, is used for before the over-sampling module carries out over-sampling to the failure operation data, to the failure
Operation data is removed dryness.
10. the fault detection system of water cooler according to claim 8, which is characterized in that the model creation module
For carrying out characterisitic parameter recurrence according to the failure operation data in multiple Mishap Databases respectively, corresponded respectively to foundation more
Multiple fault characteristic parametric prediction models of a Mishap Database.
11. the fault detection system of water cooler according to claim 8, which is characterized in that the fault diagnosis module
For determining the operation data predicted value of water cooler according to the fault characteristic parametric prediction model, and obtain the cooling-water machine
Residual error between the operation data of group and the operation data predicted value of the water cooler, and according to residual error judgement
Water cooler whether there is failure.
12. the fault detection system of water cooler according to claim 7, which is characterized in that the acquisition module is used for
It is tested according to the failure operation of water cooler, obtains the failure operation data of the water cooler, and/or, water cooler is sent out
Failure operation data of the history data as water cooler when raw failure.
13. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that be stored thereon with cold water
The fault detection program of unit realizes that claim 1-6 is any when the fault detection program of the water cooler is executed by processor
The fault detection method of the water cooler.
14. a kind of water cooler, which is characterized in that on a memory and can be in processor including memory, processor and storage
The fault detection program of the water cooler of upper operation, the realization when processor executes the fault detection program of the water cooler
The fault detection method of any water cooler of claim 1-6.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910637549.4A CN110388773A (en) | 2019-07-15 | 2019-07-15 | Fault detection method, system and the water cooler of water cooler |
PCT/CN2020/084705 WO2021008176A1 (en) | 2019-07-15 | 2020-04-14 | Fault detection method and system for water chilling unit, and water chilling unit |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910637549.4A CN110388773A (en) | 2019-07-15 | 2019-07-15 | Fault detection method, system and the water cooler of water cooler |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110388773A true CN110388773A (en) | 2019-10-29 |
Family
ID=68284985
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910637549.4A Pending CN110388773A (en) | 2019-07-15 | 2019-07-15 | Fault detection method, system and the water cooler of water cooler |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110388773A (en) |
WO (1) | WO2021008176A1 (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112040480A (en) * | 2020-10-12 | 2020-12-04 | 珠海市鸿瑞信息技术股份有限公司 | Industrial control system industrial protocol communication safety prevention and control method based on 5G communication |
CN112161377A (en) * | 2020-09-08 | 2021-01-01 | 珠海格力电器股份有限公司 | Unit fault classification processing method and device and air conditioning unit |
WO2021008176A1 (en) * | 2019-07-15 | 2021-01-21 | 重庆美的通用制冷设备有限公司 | Fault detection method and system for water chilling unit, and water chilling unit |
CN113609187A (en) * | 2021-07-23 | 2021-11-05 | 四川虹美智能科技有限公司 | Fault diagnosis method and system based on big data |
CN115014001A (en) * | 2022-05-13 | 2022-09-06 | 吉林建筑大学 | Heat recovery refrigeration system of air-cooled heat pump unit and heat recovery refrigeration method thereof |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114396704B (en) * | 2021-12-02 | 2023-04-21 | 珠海横琴能源发展有限公司 | Water chilling unit health diagnosis method and system based on big data analysis |
CN114838968B (en) * | 2022-04-28 | 2023-10-20 | 江苏一万节能科技股份有限公司 | Air conditioner fault detection method and system based on cold water cooling test |
CN116167313B (en) * | 2023-02-22 | 2023-09-12 | 深圳市摩尔芯创科技有限公司 | Training data generation method and system for integrated circuit design |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103033362A (en) * | 2012-12-31 | 2013-04-10 | 湖南大学 | Gear fault diagnosis method based on improving multivariable predictive models |
CN104697704A (en) * | 2015-03-13 | 2015-06-10 | 芜湖凯博实业股份有限公司 | Method for detecting discharge pressure faults of water chilling unit |
CN105318905A (en) * | 2014-12-30 | 2016-02-10 | 国家电网公司 | Fault diagnosis method of sensor of thermal power plant thermodynamic system |
US20170356771A1 (en) * | 2013-04-29 | 2017-12-14 | Emerson Electric (Us) Holding Corporation (Chile) Limitada | Selective Decimation and Analysis of Oversampled Data |
CN109540562A (en) * | 2018-12-12 | 2019-03-29 | 上海理工大学 | A kind of water cooler method for diagnosing faults |
CN109784574A (en) * | 2019-01-24 | 2019-05-21 | 新奥数能科技有限公司 | The prediction technique and device of equipment state, storage medium, electronic device |
CN109882441A (en) * | 2019-03-11 | 2019-06-14 | 重庆美的通用制冷设备有限公司 | Anti-surge control method and compression device |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110388773A (en) * | 2019-07-15 | 2019-10-29 | 重庆美的通用制冷设备有限公司 | Fault detection method, system and the water cooler of water cooler |
-
2019
- 2019-07-15 CN CN201910637549.4A patent/CN110388773A/en active Pending
-
2020
- 2020-04-14 WO PCT/CN2020/084705 patent/WO2021008176A1/en active Application Filing
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103033362A (en) * | 2012-12-31 | 2013-04-10 | 湖南大学 | Gear fault diagnosis method based on improving multivariable predictive models |
US20170356771A1 (en) * | 2013-04-29 | 2017-12-14 | Emerson Electric (Us) Holding Corporation (Chile) Limitada | Selective Decimation and Analysis of Oversampled Data |
CN105318905A (en) * | 2014-12-30 | 2016-02-10 | 国家电网公司 | Fault diagnosis method of sensor of thermal power plant thermodynamic system |
CN104697704A (en) * | 2015-03-13 | 2015-06-10 | 芜湖凯博实业股份有限公司 | Method for detecting discharge pressure faults of water chilling unit |
CN109540562A (en) * | 2018-12-12 | 2019-03-29 | 上海理工大学 | A kind of water cooler method for diagnosing faults |
CN109784574A (en) * | 2019-01-24 | 2019-05-21 | 新奥数能科技有限公司 | The prediction technique and device of equipment state, storage medium, electronic device |
CN109882441A (en) * | 2019-03-11 | 2019-06-14 | 重庆美的通用制冷设备有限公司 | Anti-surge control method and compression device |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021008176A1 (en) * | 2019-07-15 | 2021-01-21 | 重庆美的通用制冷设备有限公司 | Fault detection method and system for water chilling unit, and water chilling unit |
CN112161377A (en) * | 2020-09-08 | 2021-01-01 | 珠海格力电器股份有限公司 | Unit fault classification processing method and device and air conditioning unit |
CN112040480A (en) * | 2020-10-12 | 2020-12-04 | 珠海市鸿瑞信息技术股份有限公司 | Industrial control system industrial protocol communication safety prevention and control method based on 5G communication |
CN112040480B (en) * | 2020-10-12 | 2021-04-27 | 珠海市鸿瑞信息技术股份有限公司 | Industrial control system industrial protocol communication safety prevention and control method based on 5G communication |
CN113609187A (en) * | 2021-07-23 | 2021-11-05 | 四川虹美智能科技有限公司 | Fault diagnosis method and system based on big data |
CN115014001A (en) * | 2022-05-13 | 2022-09-06 | 吉林建筑大学 | Heat recovery refrigeration system of air-cooled heat pump unit and heat recovery refrigeration method thereof |
Also Published As
Publication number | Publication date |
---|---|
WO2021008176A1 (en) | 2021-01-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110388773A (en) | Fault detection method, system and the water cooler of water cooler | |
CN111209131B (en) | Method and system for determining faults of heterogeneous system based on machine learning | |
KR101713985B1 (en) | Method and apparatus for prediction maintenance | |
CN108604360B (en) | Facility abnormity monitoring method and system | |
KR101044744B1 (en) | Operating ? Maintenance System and Method for Power Distribution System Facility Based on Reliability | |
CN108518804A (en) | A kind of machine room humiture environmental forecasting method and system | |
CN108027611B (en) | Decision assistance system and method for machine maintenance using expert opinion supervised decision mode learning | |
CN106201804A (en) | The device of a kind of measuring and calculation mainboard, method and system | |
Fan et al. | Fault diagnosis method for lithium-ion batteries in electric vehicles using generalized dimensionless indicator and local outlier factor | |
CN115358155A (en) | Power big data abnormity early warning method, device, equipment and readable storage medium | |
CN114862275B (en) | Storage logistics system reliability assessment method and system based on digital twin model | |
CN111915026A (en) | Fault processing method and device, electronic equipment and storage medium | |
CN117114454B (en) | DC sleeve state evaluation method and system based on Apriori algorithm | |
CN110174878A (en) | A kind of unmanned intelligence equipment is healthy and ensures integrated management general-purpose system | |
CN111994137A (en) | Alarm analysis method based on railway signal centralized monitoring | |
CN115237086A (en) | Decision support in industrial plants | |
CN117474357A (en) | Power distribution room operation and maintenance management method and system based on deep learning | |
CN117854013A (en) | Fire monitoring system and method for electrical equipment | |
CN103077441A (en) | Self-recognition electronic product prognostic and health management (PHM) method | |
CN112926756A (en) | Application method of AI (AI) maintenance knowledge base of central air-conditioning equipment | |
CN117408162A (en) | Power grid fault control method based on digital twin | |
KR102340395B1 (en) | Apparatus for diagnosing plant failure and method therefor | |
CN105302476B (en) | A kind of reliability data online acquisition for nuclear power plant equipment analyzes storage system and its storage method | |
JP7062505B2 (en) | Equipment management support system | |
CN111314110A (en) | Fault early warning method for distributed system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191029 |
|
RJ01 | Rejection of invention patent application after publication |